What it does
Get the human's Briefing — the app's one page to start the day from, built by the same rules: (1) agents: what agents did since since — tasks shipped, runs that failed or are still running, how many tasks were handed to the human, which agents ran; (2) needs_you: everything parked on the human (a plan to approve, a result to sign off, a question), longest-waiting first; (3) priorities: today's top open tasks — overdue, due today, planned for today, or urgent — each with why it's on the list and where it stands, plus what was finished today; (4) calendar: today's events and the Plan my day blocks (see get_todays_plan). Every task carries its url. since (ISO instant) is when the human was last here; omit it for the last 12 hours, and it never reaches back more than 7 days. Use it for a morning briefing or "catch me up".
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
since | string | Optional | ISO 8601 instant the agent summary starts from. Default: 12 hours ago. Clamped to the last 7 days. |
Annotations
The hints the server sends with this tool. A host reads them to decide whether to ask you before a call.
- Read-only
readOnlyHint: true - Changes nothing.
- Destructive
destructiveHint: false - Only adds or reads; nothing already there is removed or overwritten.
- Idempotent
idempotentHint: — - Doesn't apply: the tool changes nothing.
- Open world
openWorldHint: false - Touches only your own Done account.
Which tokens can call it
A connection made with OAuth has full access. A token from Settings → Agent access → Extra MCP tokens can be narrowed, and a narrowed token never sees beyond its project or workspace.
- Full accessAllowed
- Read-only tokenAllowed
- Single-project tokenRefused
- Single-workspace tokenRefused
Try it
With Done connected, ask your assistant something like:
“Brief me: what did my agents do overnight, and what needs me?”
Connect Done to your assistant
One MCP endpoint per account, over OAuth or a token. Step-by-step setup for each client: